Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    numbers, ratios, and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DIFF
    0.38
    killing
    0.38
    ⎢
    0.37
    BorderStyle
    0.37
    щает
    0.36
     wskaz
    0.36
    윕
    0.36
     عمليه
    0.36
    Ị
    0.36
    lenie
    0.36
    POSITIVE LOGITS
    ێن
    0.42
     adopted
    0.39
     답
    0.39
     ऑड
    0.38
     മൊ
    0.38
    arab
    0.38
    답
    0.38
     pemer
    0.37
     Miss
    0.36
     muss
    0.36
    Act Density 0.003%

    No Known Activations